© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 271
    Prev
    Next
    INDEX
    Explanations

    phrases indicating established knowledge or practices over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DataAnnotations
    -0.76
    FieldBuilder
    -0.72
    aarrggbb
    -0.66
    RenderAtEndOf
    -0.63
    protoimpl
    -0.62
    tagext
    -0.61
    raisemb
    -0.60
     tslint
    -0.58
    IUrlHelper
    -0.58
     parteci
    -0.57
    POSITIVE LOGITS
     traditionally
    1.01
     always
    0.89
     Traditionally
    0.84
     conventionally
    0.81
     historically
    0.81
    Historically
    0.79
     routinely
    0.77
     Always
    0.75
    Siempre
    0.74
     usually
    0.74
    Activations Density 0.674%

    No Known Activations